CVE-2022-33281

Memory corruption due to improper validation of array index in computer vision while testing EVA kernel without sending any frames...

CVE-2022-24957

DHC Vision eQMS through 5.4.8.322 has Persistent XSS due to insufficient encoding of untrusted input/output. To exploit the vulnerability, the attacker has to create or edit a new information object and use the XSS payload as the name. Any user that opens the object's version or history tab will ...

CVE-2022-24003

Exposure of Sensitive Information vulnerability in Bixby Vision prior to version 3.7.50.6 allows attackers to access internal data of Bixby Vision via unprotected intent...

CVE-2022-35890

An issue was discovered in Inductive Automation Ignition before 7.9.20 and 8.x before 8.1.17. Designer and Vision Client Session IDs are mishandled. An attacker can determine which session IDs were generated in the past and then hijack sessions assigned to these IDs via Randy...

CVE-2021-30046

VIGRA Computer Vision Library Version-1-11-1 contains a segmentation fault vulnerability in the impex.hxx readimageband function, in which a crafted file can cause a denial of service...

CVE-2021-36134

Out of bounds write vulnerability in the JPEG parsing code of Netop Vision Pro up to and including 9.7.2 allows an adjacent unauthenticated attacker to write to arbitrary memory potentially leading to a Denial of Service DoS...

CVE-2021-25467

Assuming system privilege is gained, possible buffer overflow vulnerabilities in the Vision DSP kernel driver prior to SMR Oct-2021 Release 1 allows privilege escalation to Root by hijacking loaded library...

CVE-2020-9529

Firmware developed by Shenzhen Hichip Vision Technology V6 through V20, as used by many different vendors in millions of Internet of Things devices, suffers from a privilege escalation vulnerability that allows attackers on the local network to reset the device's administrator password. This...

CVE-2020-6848

Axper Vision II 4 devices allow XSS via the DEVICENAME aka Device Name parameter to the configWebParams.cgi URI...

CVE-2020-25167

OSIsoft PI Vision 2020 versions prior to 3.5.0 could disclose information to a user with insufficient privileges for an AF attribute...

CVE-2019-18271

OSIsoft PI Vision, All versions of PI Vision prior to 2019. The affected product is vulnerable to a cross-site request forgery that may be introduced on the PI Vision administration site...

CVE-2013-0139

The Arecont Vision AV1355DN MegaDome camera allows remote attackers to cause a denial of service video-capture outage via a packet to UDP port 69...

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models Via Objective-Decoupled Optimization

Vision-Language-Action VLA models have advanced robotic control by enabling end-to-end decision-making directly from multimodal inputs. However, their tightly coupled architectures expose novel security vulnerabilities. Unlike traditional adversarial perturbations, backdoor attacks represent a...

Are Vision-Language Models Safe in the Wild? A Meme-Based Benchmark Study

Rapid deployment of vision-language models VLMs magnifies safety risks, yet most evaluations rely on artificial images. This study asks: How safe are current VLMs when confronted with meme images that ordinary users share? To investigate this question, we introduce MemeSafetyBench, a...

FragFake: a Dataset for Fine-Grained Detection of Edited Images with Vision Language Models

Fine-grained edited image detection of localized edits in images is crucial for assessing content authenticity, especially given that modern diffusion models and image editing methods can produce highly realistic manipulations. However, this domain faces three challenges: 1 Binary classifiers yie...

Blind Spot Navigation: Evolutionary Discovery of Sensitive Semantic Concepts for LVLMs

Whitepaper called Blind Spot Navigation: Evolutionary Discovery Of Sensitive Semantic Concepts For LVLMs...

Beyond Text: Unveiling Privacy Vulnerabilities in Multi-Modal Retrieval-Augmented Generation

Multimodal Retrieval-Augmented Generation MRAG systems enhance LMMs by integrating external multimodal databases, but introduce unexplored privacy vulnerabilities. While text-based RAG privacy risks have been studied, multimodal data presents unique challenges. We provide the first systematic...

SUSE CVE-2025-31215

The issue was addressed with improved checks. This issue is fixed in Safari 18.5, iOS 18.5 and iPadOS 18.5, iPadOS 17.7.7, macOS Sequoia 15.5, tvOS 18.5, visionOS 2.5, watchOS 11.5. Processing maliciously crafted web content may lead to an unexpected process crash...

Friday Squid Blogging: Pet Squid Simulation

From Hackaday.com, this is a neural network simulation of a pet squid. Autonomous Behavior: The squid moves autonomously, making decisions based on his current state hunger, sleepiness, etc.. Implements a vision cone for food detection, simulating realistic foraging behavior. Neural network can...

Diverging Towards Hallucination: Detection of Failures in Vision-Language Models Via Multi-Token Aggregation

Vision-language models VLMs now rival human performance on many multimodal tasks, yet they still hallucinate objects or generate unsafe text. Current hallucination detectors, e.g., single-token linear probing SLP and PTrue, typically analyze only the logit of the first generated token or just its...